Uses of Class
opennlp.tools.ml.maxent.quasinewton.LineSearch.LineSearchResult

Packages that use LineSearch.LineSearchResult

Package	Description
opennlp.tools.ml.maxent.quasinewton

Uses of LineSearch.LineSearchResult in opennlp.tools.ml.maxent.quasinewton

Methods in opennlp.tools.ml.maxent.quasinewton that return LineSearch.LineSearchResult

Modifier and Type	Method and Description
static LineSearch.LineSearchResult	LineSearch.LineSearchResult.getInitialObject(double valueAtX, double[] gradAtX, double[] x) Initial linear search object.
static LineSearch.LineSearchResult	LineSearch.LineSearchResult.getInitialObject(double valueAtX, double[] gradAtX, double[] pseudoGradAtX, double[] x, double[] signX, int fctEvalCount)
static LineSearch.LineSearchResult	LineSearch.LineSearchResult.getInitialObjectForL1(double valueAtX, double[] gradAtX, double[] pseudoGradAtX, double[] x) Initial linear search object for L1-regularization.

Methods in opennlp.tools.ml.maxent.quasinewton with parameters of type LineSearch.LineSearchResult

Modifier and Type	Method and Description
static void	LineSearch.doConstrainedLineSearch(Function function, double[] direction, LineSearch.LineSearchResult lsr, double l1Cost, double initialStepSize) Constrained line search (see section 3.2 in the paper "Scalable Training of L1-Regularized Log-Linear Models", Andrew et al.
static void	LineSearch.doLineSearch(Function function, double[] direction, LineSearch.LineSearchResult lsr, double initialStepSize) Backtracking line search (see Nocedal & Wright 2006, Numerical Optimization, p.